You might like
The New England Journal of Medicine (@NEJM) today published a peer-reviewed original paper with the results of a landmark clinical trial of our PRIMA brain-computer interface (BCI) retinal implant.
Excited to share that our paper on modeling the Human Visual System with @meenakshik93 and Ishaan Chadha has been published under #CCN2025 (8-page paper track)! arxiv.org/pdf/2410.14031 (1/n)
MIT neuroscientists have identified parts of the brain’s visual cortex that respond preferentially when we look at “things” — that is, solid objects like a bouncing ball. Other brain regions are more activated when looking at “stuff” — liquids or granular substances such as sand.
🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective biorxiv.org/content/10.110…
🚀 New Open-Source Release! PyTorchTNN 🚀 A PyTorch package for building biologically-plausible temporal neural networks (TNNs)—unrolling neural network computation layer-by-layer through time, inspired by cortical processing. PyTorchTNN naturally integrates into the…
🧵0/7 🚨 Spotlight @ICML2025 🚨 Chi-Ning and Hang have been thinking deeply about how feature learning reshapes neural manifolds, and what that tells us about generalization and inductive bias in brains and machines. They put together the thread below, which I’m sharing on…
If the neocortex runs a canonical computation, what is it? The Thousand Brains Theory proposes a sensorimotor algorithm where every column models the world using reference frames 🧠 In the new video, we explore all 6 cortical layers to reveal the biological blueprint:…
youtube.com
YouTube
A Fundamental Unit Of Intelligence
#ICML #cognition #GrowAI We spent 2 years carefully curated every single experiment (i.e. object permanence, A-not-B task, visual cliff task) in this dataset (total: 1503 classic experiments spanning 12 core cognitive concepts). We spent another year to get 230 MLLMs evaluated…
How is high-level visual cortex organized? In a new preprint with @martin_hebart & @KathaDobs, we show that category-selective areas encode a rich, multidimensional feature space 🌈 biorxiv.org/content/10.110… 🧵 1/n
A very well-written piece on how LLMs' successes can be attributed to learning from the shadows of human intelligence on Plato's cave
I always found it puzzling how language models learn so much from next-token prediction, while video models learn so little from next frame prediction. Maybe it's because LLMs are actually brain scanners in disguise. Idle musings in my new blog post: sergeylevine.substack.com/p/language-mod…
This is an ongoing thread for my series, "30 Essays to Make You Love Biology." ❤️🧬 I'll pin it on my profile.
The importance of stupidity in scientific research by Martin Schwartz (2008)
Why is backpropagation biologically implausible? And what might the brain do instead? 🧠 In the newest video we explore Predictive Coding – a biologically-inspired learning algorithm and derive it from scratch This was one of my favorite videos to make so far :)…
youtube.com
YouTube
Learning Algorithm Of Biological Networks
In a study now out in @eLife, @GeorginJacob @PramodRT9 and I have some exciting results: a novel computation that helps the brain solve disparate visual tasks, a novel brain region that performs this computation....what's not to like?! Read on.... 1/n elifesciences.org/articles/93033
We built an AI assistant that plays Minecraft with you. Start building a house—it figures out what you’re doing and jumps in to help. This assistant *wasn't* trained with RLHF. Instead, it's powered by *assistance games*, a better path forward for building AI assistants. 🧵
Many apparent disagreements over the utility of neural manifolds come from a lack of clarity on what the term really encompasses, argues @mattperich. thetransmitter.org/neural-dynamic…
In a new study, out now in Attention Perception & Psychophysics, Thomas Cherian (@copy2thomas) and I have some exciting insights into what we see when an object is occluded. Like all good things, the origin of this study was simple curiosity. Consider the picture below: 1/25
OpenAI, Google and Anthropic are struggling to build more advanced AI news.ycombinator.com/item?id=421258…
Thank you @_TheTransmitter & @JordanCollver for this piece about the power of science comics! Science has the biggest impact when it can reach the most people. Science comics invite us to discuss research creatively & accessibly. Article 👇 & a quick 🧵thetransmitter.org/craft-and-care…
I'm a physicist now 😎
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
United States Trends
- 1. Wemby 30.9K posts
- 2. Steph 66.1K posts
- 3. Spurs 30.4K posts
- 4. Draymond 12.6K posts
- 5. Clemson 11.1K posts
- 6. Louisville 10.9K posts
- 7. #SmackDown 50.3K posts
- 8. Zack Ryder 15.5K posts
- 9. Aaron Fox 2,142 posts
- 10. Harden 13.7K posts
- 11. #DubNation 1,978 posts
- 12. Brohm 1,639 posts
- 13. Dabo 1,977 posts
- 14. Massie 53.8K posts
- 15. Marjorie Taylor Greene 44.2K posts
- 16. Landry Shamet 5,792 posts
- 17. UCLA 8,467 posts
- 18. #OPLive 2,450 posts
- 19. Mitch Johnson N/A
- 20. Matt Cardona 2,830 posts
You might like
-
Arya
@accordingtoarya -
manish rajani
@manishxrajani -
Gaurav Bhatnagar
@bhatnagarg -
retired funny guy
@nitantpandya -
cheese
@minkshasthots -
Jeevesh Saxena
@jeeveshhh -
D
@lact0sefr3e -
Soham De
@actuallysoham -
coffee mugs in pfp
@kartanekaramko -
The Edict Sports @ Ashoka University
@edict_sports -
sneha kalyani
@superonlida -
Kartikeya Reddy
@Kartikeya_Reddy -
Horseshoe
@horseshoespeaks
Something went wrong.
Something went wrong.